Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 18895
    Prev
    Next
    INDEX
    Explanations

    capital letters indicating section headers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'C' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yamaha
    -0.70
     Tinder
    -0.66
     timeout
    -0.65
     bottleneck
    -0.62
    uyomi
    -0.62
     steroids
    -0.61
    ĸļ
    -0.61
    ãĥĦ
    -0.61
     Sov
    -0.61
     Gors
    -0.61
    POSITIVE LOGITS
    URRENT
    1.25
    overed
    1.25
    ategories
    1.23
    onsequ
    1.20
    ologne
    1.18
    ursed
    1.16
    urses
    1.15
    rouch
    1.14
    ultural
    1.14
    ancel
    1.13
    Activations Density 0.057%

    No Known Activations